JP2018503799A - Breath print sensor system, smart inhaler and method for personal identification - Google Patents

Abstract

A breath print sensor system for verifying a person's identity using a gas made by the person is disclosed. This breath print sensor system is based on one or more first sensors having a first response characteristic to a compound in a gas and the exposure of the one or more first sensors to a human-made gas One or more processors configured to receive a set of test data provided by one or more first sensors and determine whether the set of test data confirms the identity of the person Including. Some aspects of the present disclosure relate to a smart inhaler system that uses a breath print sensor to assist in delivering a drug to a user via inhalation. A method for operating a breath print sensor and smart inhaler system and a computer readable medium for performing the method are also disclosed.

Description

Priority Data This patent document is a priority and benefit of U.S. Provisional Patent Application No. 62 / 065,465 filed Oct. 17, 2014, named BREATHPRINT SENSOR SYSTEMS, SMART INHALERS AND METHODS FOR PERSONAL IDENTIFICATION. Claims the priority and interest of U.S. Patent Application No. 14 / 791,049, filed July 2, 2015, named BREATHPRINT SENSOR SYSTEMS, SMART INHALERS AND METHODS FOR PERSONAL IDENTIFICATION, filed July 2, 2015. is there. Both U.S. Patent Application No. 14 / 791,049 and U.S. Provisional Application No. 62 / 065,465 are hereby incorporated by reference in their entirety for all purposes.

  The present disclosure relates generally to personal identification. More specifically, the present disclosure relates to verification of a person's identity using a gas created by the person, such as a gas in a person's breath.

  Require that person to provide a password or other information that only that person knows, check the photo ID card that carries the person's photo and related information such as name, gender, and age Various to verify a person's identity, such as taking a person's unique biometric sample (for example, a fingerprint or retinal scan) from that person, or examining a unique token given only to that person There is a conventional way. These conventional techniques are still widely used, tedious and time consuming to implement.

Sinues, et al. (2013), Human Breath Analysis May Support the Existence of Individual Metabolic Phenotypes, PLOS One

  Traditional health care practices have experienced various problems in drug administration, i.e. the patient may receive the wrong drug, the correct drug may be delivered to the wrong patient, or the correct drug May be administered at the wrong dose. One way to consider the problem of drug administration is compliance, ie whether the patient is taking the drug as prescribed. Traditional healthcare organizations employ personnel to perform manual containment and balancing, for example using the clipboard to enter drug information into physical charts for tracking and analysis. These conventional techniques are inefficient and prone to human error. The effectiveness of these conventional techniques is further diminished because the infrastructure to ensure compliance is not available at home when the patient is in a home care setting rather than a clinical setting. Therefore, it is desirable to have a reliable system for providing and using compliance information.

  Some embodiments of the disclosed systems, methods, apparatus, and computer readable media have multiple aspects, any one of which is responsible for the desired attributes disclosed herein. It is not borne alone.

  Some aspects of the present disclosure provide a breathprint sensor for verifying the identity of a particular person, such as a patient. Some aspects of the present disclosure relate to a smart inhaler system that uses a breath print sensor to assist in delivering a drug to a patient via inhalation.

  One aspect of the subject matter described in this disclosure is implemented in a breath print sensor system for verifying a person's identity using, for example, a gas created by the person via exhalation, secretion, excretion, release, and excretion. Can be done. The breath print sensor system includes one or more first sensors having a first response characteristic for a compound in a gas. The one or more first sensors are configured to output sensor data representing the first response characteristic. The breath print sensor system also includes one or more processors in communication with the one or more first sensors. The one or more processors receive a set of test data provided by the one or more first sensors based on the exposure of the one or more first sensors to the gas during the test phase. Is set to determine whether the person's identity is confirmed.

  In some embodiments, the breath print sensor system further includes one or more second sensors for identifying biological or environmental conditions. The one or more second sensors have a second response characteristic for the compound in the gas. The one or more second sensors are configured to output supplemental sensor data representative of the second response characteristic. One or more processors of the breath print sensor system are further in communication with the one or more second sensors. The one or more processors are provided by one or more second sensors based on (a) exposure of the one or more second sensors to a gas created by the person during the test phase. And (b) identifying a biological or environmental condition associated with the set of supplemental sensor data, and (c) providing information indicative of the biological or environmental condition. Composed.

  In some embodiments, the breath print sensor system pre-processes the test data and validates the pre-processed test data when (i) the pattern of the test data is recognized as belonging to the person. And (ii) by using a pattern classifier to classify into one of multiple classes that include unidentified identities when the pattern of test data is recognized as not belonging to the person Determine whether the set of test data confirms the person's identity. In some embodiments, the pattern classifier comprises a neural network pattern classifier.

  In some implementations, the one or more processors are further configured to train the pattern classifier from one or more sets of training data. In some embodiments, training the pattern classifier from one or more sets of training data includes one of one or more first sensors to the gas created by the person during the training phase. Receiving one or more sets of positive training data provided by one or more first sensors based on one or more exposures and patterning one or more sets of positive training data Providing to the classifier and notifying the pattern classifier that one or more sets of positive training data belong to the person. In some embodiments, training the pattern classifier from one or more sets of training data includes the one or more first sensors to a gas that was not created by the person during the training phase. Receiving one or more sets of negative training data provided by one or more first sensors based on one or more exposures and receiving one or more sets of negative training data Providing further to the pattern classifier and notifying the pattern classifier that one or more sets of negative training data do not belong to the person.

  In some embodiments, one or more first sensors of the breath print sensor system described herein include a conductive polymer, a conductive polymer composite, an intrinsically conductive polymer, And any combination thereof. In some embodiments, the one or more first sensors have a surface temperature of the one or more first sensors of about 200 ° C. or less, about 100 ° C. or less, about −50 ° C. and about 100 ° C. Is further configured to obtain sensor data during or between about 0 ° C. and about 50 ° C. In some implementations, the one or more first sensors of the breath print sensor system described herein are such that the surface temperature of the one or more first sensors is not modulated or substantially. Further configured to obtain sensor data when constant. In some embodiments, each sensor includes a polymer layer having a variable conductance based on exposure to volatile organic compounds (VOC) in the gas.

  In some embodiments, any of the breath print sensor systems described herein further includes a memory configured to store sensor data and / or information derived from the sensor data.

  In some embodiments, one or more processors of any of the breath print sensors are further configured to derive test feature vectors from test data via feature extraction. In some embodiments, the one or more processors compare the test feature vector with a training feature vector derived from the training data and, based on the comparison, whether the test data confirms the person's identity. Further configured to determine.

  In some embodiments, the breath print sensor system includes an inhaler device adapted to deliver a drug to the person via inhalation when the inhaler device is received by the person, and the breath print sensor system and the inhaler. It further includes a control system in communication with the device, and an interface system for inputting and / or outputting data to the breath printing system, the inhaler device, and / or the control system. The control system receives information from the breath print sensor system, the information indicating whether the person's identity is verified and configured to control the operation of the inhaler device according to the received information.

  Another aspect of the subject matter described in this disclosure can be implemented in a smart inhaler system for delivering drugs to a person by inhalation. The smart inhaler system includes a breath print sensor system configured to verify the identity of the person using gas created by the person, and via inhalation when the inhaler device is received by the person. An inhaler device adapted to deliver a drug to the person, and a breath print sensor system and a control system in communication with the inhaler device. The control system receives information from the breath print sensor system, the information indicating whether the person's identity is verified and configured to control the operation of the inhaler device according to the received information. In some embodiments of the smart inhaler system, controlling the operation of the inhaler device according to the received information includes controlling the delivery of the drug according to the received information. In some embodiments, the smart inhaler system further includes an interface system for inputting data into and / or outputting data from the breath print sensor system, inhaler device, and / or control system. In some embodiments, the interface system includes a wireless network interface for exchanging data with external devices over the wireless network. In some embodiments, the interface system includes an input / output device configured to receive user input and provide information to the user. In some implementations, the input / output devices include display devices, light emitting diodes, speakers, touch sensitive input devices, buttons, haptic devices, or any combination thereof.

  In some embodiments of any of the smart inhaler systems disclosed herein, when the control system indicates that the information received from the breath print sensor system indicates that the person's identity is not verified, To provide notification to another person that an unverified person has attempted to use the inhaler device, to deactivate the inhaler device, and to provide a breath sample to the breath print sensor system Further configured to perform one or more of the following actions: prompting the person to provide alternative information not derived from the breathing sample to confirm the person's identity The

  In some embodiments of any of the smart inhaler systems disclosed herein, the control system includes a breath print sensor system and one or more processors communicatively coupled to the inhaler device. . At least one of the processors analyzes information derived from respiratory samples made by the person, determines that the person has a respiratory disorder, associates the respiratory disorder with one or more environmental conditions; One or more environmental conditions are associated with the location data and configured to create a map of the one or more environmental conditions associated with the respiratory disorder.

  In some embodiments of any of the smart inhaler systems disclosed herein, the breath print sensor system includes one or more first sensors having a first response characteristic to a compound in the gas. Wherein the one or more first sensors are configured to output sensor data representative of the first response characteristic and the first sensor to the compound in the gas One or more second sensors having two response characteristics, wherein the one or more second sensors are configured to output supplemental sensor data representative of the second response characteristics, 1 One or more second sensors. The first response characteristic is tuned to confirm the person's identity and the second response characteristic is tuned for one or more biological markers. In some embodiments, the one or more biological markers relate to the pharmacokinetics of the drug. At least one of the processors of the control system is configured to detect a drug delivered by the inhaler device using supplemental sensor data representing a second response characteristic tuned for the one or more biological markers. It is configured to determine the efficacy of the dose and to determine a drug delivery plan based on the efficacy.

  One aspect of the present disclosure includes a method for verifying a person's identity using a breath print sensor system. The breath print sensor system includes one or more first sensors having a first response characteristic for a compound in a gas. The method includes receiving a set of test data provided by one or more first sensors based on exposure of the one or more first sensors to a gas created by the person; Determining whether the set confirms the identity of the person. In some embodiments, the breath print sensor system further includes one or more second sensors having a second response characteristic for the compound in the gas. The method receives a set of supplemental sensor data provided by one or more second sensors based on exposure of the one or more second sensors to a gas created by the person; The method further includes identifying a biological condition or environmental condition associated with the set of supplemental sensor data and providing information indicative of the biological condition or environmental condition.

  In some embodiments of the method for verifying the person's identity, determining whether the test data set confirms the person's identity includes pre-processing the test data and pre-processing. (I) a confirmed identity when the pattern of test data is recognized as belonging to the person and (ii) no confirmation when the pattern of test data is recognized as not belonging to the person Using a pattern classifier to classify into one of a plurality of classes containing identities.

  In some embodiments, the method further includes training a pattern classifier from one or more sets of training data prior to classifying the preprocessed test data. In some embodiments, the step of training the pattern classifier is one based on one or more exposures of the one or more first sensors to the gas created by the person during the training phase. Or receiving one or more sets of positive training data provided by a plurality of first sensors, providing one or more sets of positive training data to a pattern classifier, Informing the pattern classifier that one or more sets of training data belong to the person.

  In some embodiments of the method described above, the step of training the pattern classifier comprises one or more of one or more first sensors to the gas that was not created by the person during the training phase. Receiving one or more sets of negative training data provided by one or more first sensors based on multiple exposures, and pattern classifiers for one or more sets of negative training data And providing to the pattern classifier that one or more sets of negative training data do not belong to the person.

  Another aspect of the present disclosure is for controlling a smart inhaler system that includes a breath print sensor system, an inhaler device, and one or more processors in communication with the breath print sensor system and the inhaler device. Including methods. The method receives from the breath print sensor system information indicating whether the person's identity is confirmed using a gas created by the person, and controls the operation of the inhaler device according to the received information. Steps. In some embodiments, controlling the operation of the inhaler device according to the received information includes controlling the delivery of the drug according to the received information.

  In some embodiments, the step of controlling the operation of the inhaler device according to the received information may be performed by an unverified person when the information received from the breath print sensor system indicates that the person's identity is not verified. Sending a notification to another person informing them that they have attempted to use the inhaler device, deactivating the inhaler device, and providing the person with a breath sample to the breath print sensor system. Performing one or more of an act of prompting and an action of prompting the person to provide alternative information not derived from the breath sample to confirm the person's identity.

  Some or all of the methods described herein may be performed by one or more devices according to instructions (eg, software) stored on non-transitory media. Such non-transitory media may include memory devices, such as those described herein, including but not limited to random access memory (RAM) devices, read only memory (ROM) devices, and the like. it can. Accordingly, other aspects of the subject matter described in this disclosure can be implemented in non-transitory media having software stored thereon. One aspect of the present disclosure is a non-transitory computer readable medium that stores computer readable program code executed by one or more processors, the program code having a first response characteristic to a compound in a gas. A breath print sensor system including one or more first sensors is provided by one or more first sensors based on the exposure of the one or more first sensors to a gas made by a person A non-transitory computer readable medium is provided that includes instructions for receiving a set of additional test data and instructions for determining whether the set of test data confirms the identity of the person.

  In some embodiments, determining whether a set of test data confirms the person's identity includes pre-processing the test data and (i) a pattern of test data. One of several classes, including a confirmed identity when a person is recognized as belonging to the person and (ii) an unidentified identity when a pattern of test data is recognized as not belonging to the person Using a pattern classifier to classify.

  In some embodiments, the computer readable program code causes the breath print sensor system to include one or more second sensors based on the exposure of the one or more second sensors to a gas created by the person. Instructions for receiving a set of supplemental sensor data provided by the sensor, instructions for identifying a biological or environmental condition associated with the set of supplemental sensor data, and providing information indicative of the biological or environmental condition The breath print sensor system further includes one or more second sensors having a second response characteristic for the compound in the gas.

  One aspect of the present disclosure is a non-transitory computer readable medium that stores computer readable program code that is executed by one or more processors, the program code including a breath print sensor system and an inhaler device. Causing the inhaler system to receive information from the breath print sensor system indicating whether the person's identity is confirmed using a gas made by the person and to control the operation of the inhaler device according to the received information A non-transitory computer-readable medium is provided that includes instructions configured for:

  The details of one or more implementations of the subject matter described in this specification are set forth in the accompanying drawings and the description below. Other features, aspects, and advantages will be apparent from the description, drawings, and claims. Note that the relative dimensions of the following drawings may not be drawn to scale.

  The details of one or more implementations of the subject matter described in this specification are set forth in the accompanying drawings and the description below. Other features, aspects, and advantages will be apparent from the description, drawings, and claims. Note that the relative dimensions of the following drawings may not be drawn to scale. Like reference numbers and designations in the various drawings indicate like elements.

FIG. 6 is a block diagram illustrating example components of a smart inhaler system in which some aspects of the present disclosure may be implemented. FIG. 6 is a block diagram illustrating example components of a breath print sensor system in which some aspects of the present disclosure may be implemented. 2 is a flow diagram illustrating an overview of an example method for verifying a user's identity using a user's breath print. 2 is a flowchart outlining an example of a method for operating a smart inhaler system to verify a user's identity using a breath print sensor array. 1 is a block diagram illustrating an example of a system for verifying a user's identity based on a pattern classification of data from a sensor array. FIG. 2 is a schematic diagram illustrating a neural network configured to perform pattern classification to verify a user's identity. It is a figure which shows the example of the pattern of the response of the sensor array in a breath print sensor system. It is a figure which shows the example of the pattern of the response of two sensor arrays in a breath print sensor system. FIG. 6 is a block diagram illustrating example components of a system in which some aspects of the present disclosure may be implemented over a computer network.

  One way to administer drugs to a person is through inhalation. In some embodiments, the inhaler can be inserted into the person's mouth, which is the environment specific to the person using the inhaler. In some other embodiments, an electronic nasal device may be used to identify a person or confirm that a particular person is administering a drug.

  Conventional smart inhalers are used to deliver drugs such as inhaled asthma or chronic heart failure (CHF) medications as well as other medications such as inhalable powder versions of insulin. Conventional smart inhalers primarily address compliance and adherence issues. For example, conventional smart inhalers provide the right dose, the right shape, and the ability to ensure that the right drug is administered at the right time.

  Some of the disclosed embodiments are configured to facilitate the identification of a “right patient” in a manner convenient for a user such as a healthcare professional or patient. Identity validation can be useful in connection with validation of drug compliance and adherence, determination of drug efficacy and safety, and enablement of pay-per-outcome models. Ease-of-use confirmation of patient identity is particularly valuable in the case of smart wireless mobile drug delivery mechanisms. This is also useful in remote mobile trials. For example, it may be desirable to deliver an inhalable drug to multiple patients in a hospital when the drug delivery system can verify and track the identity of the patient receiving the drug. In another example, it may be useful for a physician to remotely monitor inpatient inhalable drug administration using an automated system that can verify and track the patient's identity.

  Some of the disclosed embodiments provide a system for delivering a drug by inhalation and verifying the patient's identity in a manner that is transparent to the user. Some of the disclosed embodiments determine whether the user has delivered and consumed the drug correctly by analyzing the breath exhaled by the user after the user has administered and inhaled the drug. Configured. Some of the disclosed embodiments provide smart inhalers that are operable to detect biomarkers of medical conditions by analyzing air exhaled by a user. Some of the disclosed embodiments analyze compounds contained in exhaled breath, such as volatile organic compounds (VOCs), thereby enabling the user's identity, effective administration of drugs, and / or medical conditions. A breath print indicating a biomarker is determined. Some of the disclosed embodiments include a fingerprint sensor (e.g., on a button pressed by the user) or a DNA analyzer (e.g., analyzing DNA in saliva) in a smart inhaler for user identification verification. Integrate.

  Some of the disclosed embodiments include a sensor in a smart inhaler that can be trained to recognize an individual-specific signature from the person's breath, commonly referred to herein as the person's breath print. Integrate. A signature is generally in the form of a pattern of information related to a person, which is derived from an analysis of compounds contained within that person's breath. Although a person is described in this disclosure as the provider of a respiratory sample that is analyzed to confirm that person's identity, respiration of non-human animals (e.g., mammals, birds, or reptiles) is also described herein. It should be understood that the embodiments disclosed within the document can be used to validate animal identities in a veterinary setting.

  Some embodiments of the present disclosure provide a breath print sensor system that can obtain breath prints specific to different individuals. Some embodiments of the breath print sensor system can obtain a breath print that persists over time. Some embodiments provide a cost-effective breath print sensor system for fabrication. Some implementations are suitable for application within a mobile platform.

  The breath print can be analyzed in various ways. For example, a sudden change in the breath print can signal a change in the patient's medical condition. The gas in a patient's breath is a vaporized, urine-like fluid that contains a metabolic phenotype in a pattern unique to that person. Thus, in some embodiments, an electronic sensor array such as an “electronic nose” may be incorporated to recognize VOCs in the patient's breath.

  The patient's respiratory fluid is rich in VOCs. Studies using mass spectrometry have produced breath prints characterized by m / z (molecular mass to charge ratio) of ionized compounds in the respiratory sample, for example m / z = 59 for acetone. Identified. Sinues, et al. (2013), Human Breath Analysis May Support the Existence of Individual Metabolic Phenotypes, PLOS One. However, mass spectrometry was not performed in a mobile drug delivery system due to the size and weight issues of mass spectrometry instruments. Some of the disclosed embodiments provide an electronic nose integrated into a mobile personal smart inhaler system. The electronic nose can be used to recognize a particular user by analyzing the gas exhaled or otherwise provided by the user.

  In some embodiments, an example electronic nose system utilizes an array of non-specific sensors to detect a “fingerprint” response to a person's breathing. Pattern classification and / or recognition algorithms are applied to verify the person's identity. Input respiration induces a reversible physical change in the sensing material that causes a change in the electrical properties of the sensor element (or “cell”), such as its electrical conductivity. These changes are converted into electrical signals, which are then processed prior to pattern recognition.

  In some embodiments, the electronic nose includes an array of sensors, each sensor having a polymer layer with a variable conductance based on exposure to VOCs in the gas. In some embodiments, the sensor has different response characteristics to various compounds such as VOCs. Upon exposure to vapor, the conductance of the polymer in each sensor changes in a different manner than the other sensors in the array. The pattern of sensor conductance may be related to different types of objects or object conditions.

  FIG. 1A is a block diagram illustrating example components of a smart inhaler system in which some aspects of the present disclosure may be implemented. As shown in the example in FIG. 1A, the smart inhaler system includes a breath print sensor system 152, an inhaler device 154, a control system 156, and an interface system 158. In some embodiments, the breath print sensor system 152 may be implemented according to the description associated with FIG. 1B below. Inhaler device 154 is configured to deliver a drug to a user when received by the user's mouth or nostril.

  The control system 156 is configured to control the operation of the smart inhaler system. In one example, the control system 156 is configured to control the delivery of medication by the inhaler device 154 based on information provided by the breath print sensor system 152 or the interface system 158. In various embodiments, the control system 156 is configured to control the amount, timing, and other characteristics of the drug.

  In some embodiments, the control system 156 includes a general-purpose single-chip or multi-chip processor, digital signal processor (DSP), application specific integrated circuit (ASIC), field programmable gate array (FPGA) or other programmable logic. It includes at least one of a device, discrete gate logic or transistor logic, or a discrete hardware component. In some embodiments, one or more processors of the control system 156 are communicatively coupled to the breath print sensor system and / or the inhaler device. In some embodiments, the one or more processors are configured to provide instructions for controlling the breath print sensor system and / or the inhaler device. In some embodiments, the one or more processors include a breath print sensor system and / or inhaler device, or are disposed in a housing that is attached to the breath print sensor system and / or inhaler device. In some embodiments, at least one of the processors is configured to communicate with the breath print sensor system and / or the inhaler device via a computer network. In some embodiments, the control system includes two or more processors distributed over a computer network.

  Interface system 158 includes an interface configured to input data to and / or output data from control system 156, inhaler device 154, and / or breath print sensor system 152. In some implementations, the interface system 158 communicatively connects these elements to memory (not shown in this figure) and / or external devices (eg, via wired or wireless ports). In some embodiments of the present disclosure, the interface system 158 is optional.

  In some embodiments, the interface system 158 includes a wireless network interface for remote communication with external devices, either directly or via a computer network such as an intranet or the Internet. For example, in some implementations, a smart inhaler system can communicate with an application running on a mobile device that is communicatively linked to the smart inhaler system via an interface system. In various implementations, the external device can be a diagnostic device, a physiological sensing device, an environmental sensing device, a smart watch, or a wireless phone. In some implementations, the interface allows simultaneous communication with multiple external devices. In various embodiments, the external device communicates dose information to the smart inhaler based on data from the breath print sensor system, inhaler device, and / or control system. In some embodiments, the external device communicates dose information to the smart inhaler without requiring any user input.

  In some implementations, the interface system 158 includes an input / output device configured to provide information to the user and receive user input. For example, input / output devices include one or more of display devices, light emitting diodes, speakers, touch sensitive input devices, buttons, and haptic devices. In some implementations, the input / output device can output information regarding a person's identity as determined by the breath print sensor system 152. In some embodiments, the input / output device outputs information related to drug delivery (e.g., recommended dosage or time for drug administration) based on information provided by the breath print sensor system 152. Can do. For example, the control system 156 can receive information from a biological sensor of the breath print sensor system that indicates the biological condition of the user. In response, the control system 156 can control the input / output device to output recommendations regarding the dose of the drug based on the biological conditions. For example, if the control system determines that a biomarker indicative of a severe level of asthma, such as NO (Nitric Oxide), is present in the user's breath, the smart inhaler system may receive an asthma drug via the input / output device. Recommended doses can be provided. In various embodiments, the input / output device can output a dose (or other information) recommended to the user in the form of vision, hearing, touch, smell, or taste. In some embodiments, the control system 156 can determine environmental conditions from sensor data provided by environmental sensors, and the input / output device can alert about environmental risks, such as increased levels of allergens or contaminants. Further configured to provide

  In some embodiments, the smart inhaler system includes a storage medium configured to store data representing the operation of the breath print sensor system or components thereof. In these embodiments, the smart inhaler system can record information at different times, such as patient identity, time of drug administration, and drug dosage. In some embodiments, such stored information can be analyzed and / or used to control the inhaler. For example, the inhaler can adjust its dosage based on information regarding previous drug administration, biological conditions, or environmental conditions.

  FIG. 1B is a block diagram illustrating example components of a breath print sensor system 152 in which some aspects of the present disclosure may be implemented. The breath print sensor system 152 may be implemented in the smart inhaler system 150 shown in FIG. 1A. In this example, the breath print sensor system 152 includes a plurality of first sensors 160 having a first response characteristic for compounds in the gas. The first sensor 160 is configured to output sensor data representing the first response characteristic. In this example, the breath print sensor system 152 also includes one or more second sensors 162, described further below. The dashed line at block 162 in FIG. 1B indicates that the second sensor is optional for some embodiments of the breath print sensor system. The second sensor 162 has a second response characteristic different from the first response characteristic of the first sensor 160. The second sensor 162 is configured to output sensor data representing the second response characteristic. The breath print sensor system 152 shown in this figure also includes a memory 164 configured to store sensor data. The dashed line at block 164 indicates that the memory 164 is optional in some embodiments of the breath print sensor system. In some implementations, the memory can be external to the breath print sensor system. For example, a smart inhaler system can include a memory and a breath print sensor system. The breath print sensor system does not have a built-in memory, but the smart inhaler system memory can store information obtained from the breath print sensor. In some implementations, a networked storage can store information about the breath print sensor system.

  As shown in the example in FIG. 1B, the breath print sensor system 152 includes one or more processors 166. The processor is in communication with the first sensor 160. In some embodiments including a second sensor 162 or memory 164, the processor is in communication with the second sensor 162 and memory 164. The one or more processors 166 are configured to verify an identity of a person from the sensor data provided by the first sensor 160. FIG. 2 shows an example of a process that the processor 166 may perform to determine the person's identity.

  In some embodiments, an electronic nose system is used as a sensor for the breath print sensor system 152. In some embodiments, the electronic nose system includes an array of non-specific sensors and hardware and software for performing digital signal processing and pattern classification algorithms. Electronic nose systems are used in classifying or recognizing compounds without having to break down the compound into its components. One or more gases are detected by the electronic nose system. The gas can be from the user's mouth or nostril. Some compounds in the gas originate from the user's body and provide the user's biometrics.

  In some implementations, the first sensor 160 of the breath print sensor system 152 is configured to output sensor data representative of the first response characteristic. In some embodiments, the sensor has different response characteristics to volatile organic compounds in the gas. In some embodiments, the first sensor is tuned to provide different response characteristics from person to person.

  A variety of sensor materials can be used in an electronic nose system, including but not limited to conductive polymers, conductive polymer composites, intrinsically conductive polymers, metal oxides, graphene, and other materials. . The sensor material can provide a mechanism for detecting charge transfer between the sensor and a molecule of the compound of interest.

  It may be desirable to provide a sensor configured to operate at a certain temperature under various circumstances. For example, some conventional sensors, such as metal oxide sensors, have acceptable dynamic sensitivity at relatively high temperatures, eg, greater than about 200 ° C. These conventional sensors may work well only at high temperatures. Operating a breath print sensor system with such conventional sensors may require additional energy and hardware to heat the sensor and / or gas. Thus, in some embodiments, the disclosed sensors can provide sensor data when the temperature at one or more of the sensors, i.e., the sensor surface temperature, does not exceed about 200 degrees Celsius or does not exceed about 100 degrees Celsius. Configured to obtain.

  Under some circumstances, disclosed sensor embodiments obtain sensor data when the sensor surface temperature is in a range consistent with the general operating temperature of the environment in which the user uses the breath print sensor. Configured as follows. For example, some embodiments of the disclosed sensors are configured to obtain sensor data at sensor surface temperatures from about 0 ° C. to about 50 ° C. In some other embodiments, the sensor surface temperature is within a wider temperature range to address more extreme sensing environments, such as outer space, near the Earth's poles, or the underground environment. Accordingly, some embodiments of the disclosed sensors are configured to obtain sensor data at sensor surface temperatures from about −50 ° C. to about 100 ° C. or from about −100 ° C. to about 200 ° C.

  In some embodiments, the sensor used in the breath printing system is configured to obtain sensor data at an unmodulated sensor surface temperature. For example, the unmodulated surface temperature can be a constant or substantially constant surface temperature, such as a temperature that varies without exceeding about 10 ° C. In another example, the unmodulated surface temperature is a temperature that changes passively as a result of ambient temperature, often in a gradual manner.

  In some embodiments including an electronic nose system, a conductive polymer composite is used as the sensing material of the sensor. The conductive polymer composite material includes conductive particles interspersed within the insulating polymer, such as polypyrrole and carbon black. Upon exposure to the gas, the gas penetrates the polymer and induces polymer expansion. This induced expansion of the polymer composite causes an increase in the resistance of the polymer composite because the expansion reduces the number of charge carrier conduction paths. In some embodiments, the conductive polymer composite has a response time of less than 20 seconds, or more preferably a response time of less than 10 seconds, or more preferably a response time of 2 to 4 seconds.

  In some embodiments, the conductive polymer sensor may be made from a conductive polymer composite that is inexpensive or simple to manufacture, suitable for a breath print sensor in a disposable smart inhaler. In some embodiments, the conductive polymer sensor can be of the following conditions: small amount of vapor, dilution with ambient air, changing environment (e.g., temperature, light, and airflow), low compound concentration, or high sensing speed. Data for detecting a breath print under one or more may be provided.

  The human mouth or nose provides a stable operating environment for the electronic nose with respect to temperature and humidity where the environment can provide good response conditions for the conducting polymer sensor. In some applications, the conductive polymer sensor is implemented in a disposable device that has a limited number of uses. The limited number of uses makes practical application of conductive polymer sensors even when the polymer material ages relatively quickly over time.

  The breath print sensor system 152 of FIG. 1B can optionally include one or more second sensors 162 having response characteristics that are different from the response characteristics of the first sensor 160. The second sensor is also referred to herein as an enhanced sensor herein. These second sensors 162 are provided for detecting biological or environmental conditions. In some embodiments, these second sensors 162 are tuned to determine one or more biological or environmental conditions. For example, the second sensor 162 may be tuned to provide data for determining nitric oxide (NO) levels in the user's breath that may be used to determine the severity of asthma. In another example, the second sensor 162 can be tuned to provide data for determining allergens, contaminants, and other health-related factors in the air.

  FIG. 2 is a flow diagram illustrating an overview of an example method 200 for using user breathing to validate a user identity. One aspect of the present disclosure can implement this method by executing instructions on one or more processors 166 of the breath print sensor system 152 described above in connection with FIG. 1B. As shown, the method 200 includes receiving a set of test data provided by one or more first sensors based on the exposure of the first sensor to the gas during the test phase. See block 202. In various applications, the gas during the test phase is provided by a person using a breath print sensor system to verify her / his identity. In some embodiments, the breath print sensor system can be used as part of a smart inhaler system. In some implementations, as shown in this figure, the method 200 optionally pre-processes sensor data provided by the first sensor (e.g., analog-to-digital conversion of sensor data). Or filtering of sensor data). See block 204. The sensor data may be test data that is provided during a test phase when a person uses the breath print sensor system to verify her / his identity. In some embodiments, the method 200 optionally includes test data comprising: (i) a verified identity when the test data pattern is recognized as belonging to the person; or (ii) the test data pattern is Including using pattern classifiers to classify into one of multiple classes that contain unverified identities when recognized as not belonging to a person. See block 206. In some embodiments, more than two classes are implemented, such as a “no decision” third class when the pattern of test data is between the first class and the second class according to the classifier. obtain. In some embodiments, the method 200 proceeds to determine that the test data verifies the person's identity when the pattern classifier classifies the test data as class (i). See block 208. In some embodiments, the pattern classifier is a neural network pattern classifier. Applicable neural network pattern classifiers are further described below with reference to FIG.

  In some embodiments, the pattern classifier is trained using one or more sets of training data. In some embodiments, pattern classifier training occurs during a training phase prior to the testing phase. In some embodiments, training of the pattern classifier is based on one or more exposures of the first sensor to a gas exhaled or otherwise provided by a person during the training phase. Receiving one or more sets of positive training data provided by the sensor. In some embodiments, the gas is provided by the person exhaling the gas into a device configured to receive the gas in the respiratory sample. In various embodiments, the gas may be received by an inhaler device, a mask covering the mouth or nose, a device configured to be inserted into a body cavity, and the like. The identity of the person can be tested during the testing phase after the pattern classifier has been trained. Pattern classifier training provides pattern classifiers with one or more sets of positive training data and that one or more sets of positive training data belong to the person. Further informing.

  In some embodiments, training the pattern classifier is provided by the first sensor based on one or more exposures of the first sensor to a gas that was not provided by the person during the training phase. Receiving one or more sets of negative training data, providing one or more sets of negative training data to the pattern classifier, and one or more sets of negative training data To inform the pattern classifier that it does not belong to the person. In some embodiments, negative training data may be derived from ambient inspiration, gas exhaled by control subjects, or other gases not obtained from the person.

  In some embodiments using feature extraction techniques known in the art, the breath print sensor system contrasts test feature vectors from test data, target feature vectors from positive training data, and negative training data. A feature vector can be derived. In some implementations, the breath print sensor system can compare the test feature vector to the target feature vector and determine whether the test data confirms the person's identity based on the comparison. In some implementations, the comparison of the test feature vector to the target feature vector includes determining a difference or distance between the test feature vector and the target feature vector. In some embodiments, if the difference is less than the criterion, the method proceeds to determine that the set of sensor data identifies the person based on the comparison. In some embodiments, the method can compare a test feature vector with both a target feature vector and a control feature vector, the target feature vector is derived from positive training data, and the control feature vector is: Derived from negative training data. In some embodiments, the method determines that the test data confirms the person's identity if the test feature vector is more similar to the target feature vector than the control feature vector.

  According to some embodiments, method 200 may be implemented in a non-transitory medium having software stored thereon. In some implementations, the method 200 may be performed, at least in part, by one or more processors of the sensor system (eg, the processor 166 shown in FIG. 1B). In some embodiments, the method 200 may be performed by one or more processors in the smart inhaler system 150 in FIG. 1A.

  Returning to FIG. 1A, some embodiments of the present disclosure provide a smart inhaler system 150 that includes a control system 156. The control system 156 is configured to receive information provided by the breath print sensor system 152. The information received indicates whether the person's identity is confirmed. In some embodiments, the control system 156 may include one or more processors that can analyze information from the breath print sensor system to determine whether the person's identity is verified. it can. In various embodiments, if the person's identity is verified, the control system 156 may control the drug via the inhaler device 154, such as by controlling the dosage, concentration, timing, and other aspects of the drug. Control delivery. In some embodiments, the control system may provide a separate notification to notify that an unverified person has attempted to use the smart inhaler if the identity of the person providing the breath sample to the smart inhaler is not verified. Sending notifications to a person (doctor or caregiver) or computer system, deactivating the inhaler device, urging the person to provide additional breath samples to the breath print sensor system, or the person Configured to perform one or more of the actions that prompt the person to provide alternative information to verify the identity of the person (eg, by entering a protected password). In some embodiments, the smart inhaler system can also include a fingerprint sensor, through which the person provides a fingerprint sample as alternative information to confirm his or her identity can do. In some embodiments, the control system 156 stores compliance data including identity verification results, dosages, and timing of dosage administration by the inhaler, as described below with reference to FIG. Remember in.

  In some embodiments, the smart inhaler system 150 has one or more processors as described above. In some embodiments, at least one of the processors is configured to analyze information derived from a breathing sample of the person and determine that the person has a disordered breathing. This determination may be based on data provided by one or more sensors of the breath print sensor system 152. The smart inhaler system 150 may determine the person's breathing index (e.g., rate of inhalation) to determine when the person has a disordered breathing (e.g., dyspnea or asthma attack). inhalation) or inhalation volume) can be monitored. In some embodiments, at least one of the processors is further configured to associate the respiratory disorder with one or more environmental conditions. In some embodiments, at least one of the processors is further configured to associate one or more environmental conditions with the location data and create a map of the environmental conditions associated with the respiratory disorder.

  In some embodiments, the smart inhaler system 150 is implemented as part of a system that includes a database having information regarding the use of multiple people. At least one of the processors of the smart inhaler system 150 is configured to aggregate information derived from a plurality of persons to create a map of environmental conditions associated with breathing disorders.

  In some embodiments, the smart inhaler system 150 includes one or more first sensors having a first response characteristic for a compound in the gas and one having a second response characteristic for the compound in the gas. Or a plurality of second sensors. The first sensor is configured to output sensor data representing a first response characteristic, and the second sensor is configured to output supplemental sensor data representing a second response characteristic. In some embodiments, the first response characteristic is tuned to confirm the person's identity and the second response characteristic is tuned for one or more biological markers. In some embodiments, the one or more biological markers relate to the pharmacokinetics of the drug. In some embodiments, the smart inhaler system is a biomarker in the person's breath (specific to the drug being administered) to confirm that the user is actually taking the correct drug. Test). As described elsewhere herein, a smart inhaler system may include one or more of testing data provided by a supplementary sensor of a breath print sensor system to test biological markers. A processor can be used.

  In some embodiments, the smart inhaler system records the time of drug delivery and / or dose information and stores this information in a database. In some embodiments, the smart inhaler system uses one or more processors to compare the time of delivery and / or dose information with a schedule stored in a database to determine compliance information. To do. In some embodiments, the smart inhaler system controls the inhaler device according to compliance information.

  In some embodiments, at least one processor of the smart inhaler system 150 uses the supplemental data representing the second response characteristic tuned for the one or more biological markers to use the inhaler device. Configured to determine the efficacy of the dose of the drug delivered by. In some embodiments, at least one processor of the smart inhaler system is further configured to determine a drug delivery plan based on the efficacy determined by the processor. For example, the processor may determine to increase or decrease the dosage of a drug if a compound in the patient's breath exhibits pharmacokinetic parameters that justify the change in dosage.

  In some embodiments, at least one processor of the smart inhaler system is configured to compare efficacy data for multiple persons and recognize patterns of efficacy data across the population. In these embodiments, population efficacy data may be stored in a database accessible by at least one processor of the smart inhaler system.

  In some embodiments, the smart inhaler system 150 can determine whether a person (e.g., a pilot) has consumed a drug (e.g., alcohol) and / or that person has an activity (e.g., aircraft maneuver). Can be used to determine if the patient is in a physiological state suitable for performing. In some embodiments, smart inhaler system 150 is using the device to test drug consumption using sensor data from a first sensor described elsewhere in this specification. The identity of a person (eg, an aircraft pilot) can be verified. At least one processor of the smart inhaler system is configured to use supplemental sensor data provided by the second sensor of the breath print sensor system 152 to determine whether the person has taken the drug. . The supplemental sensor data represents a second response characteristic tuned for one or more biological markers. At least one processor of the smart inhaler system is further configured to determine whether the person is in a physiological state suitable for performing the activity based on supplemental data indicating the level of the biological marker. The For example, the system can determine whether a pilot has consumed too much alcohol to safely maneuver the aircraft.

  In some embodiments, the smart inhaler system 150 can be used to monitor a person for drug addiction. In such applications, the smart inhaler system uses 1) a first sensor to confirm the person's identity, and 2) uses a second sensor that the person did not use the drug. And / or 3) send test results to a government office or agency.

  FIG. 3 shows a flowchart outlining an example of a method 300 for operating a smart inhaler system to determine a person's identity using a breath print sensor array. During the initialization or registration stage (block 302), the system receives training set data 304 and uses it to train an electronic nose that can recognize or classify a patient's breath print (block 306). ). Training set data 304 is obtained by an electronic nose system, such as the breath print sensor system 152 described in FIG. 1B. In some embodiments, the training set includes positive training data obtained from the breath of the person identified by the breath print sensor system. In some embodiments, the training set includes negative training data (eg, data from ambient air or control subjects) that was not obtained from the person's breath. In some embodiments, at this registration stage, the breath print sensor system extracts one or more target feature vectors from the person's data. In some embodiments involving negative training, the system can extract one or more control feature vectors from data that is not obtained from the person, or from extracted feature vectors or training data. Other derived information is provided to the pattern classifier to train the pattern classifier to classify breath samples as (1) an identity that is confirmed for the person or (2) an identity that is not confirmed for the person. The

During the use stage (block 308), respiratory samples are obtained as test data at various times (t _i , i = 1, 2...) (Block 310). The test data is then provided to an electronic nose system trained to recognize the user's breath print (block 312). In some embodiments, recognition of the user's breath print is accomplished by a pattern classifier as described herein (see block 318). In some embodiments, recognition of a user's breathprint is determined by a binary classification using data derived from respiratory samples, ie, “user identity is verified” and “user identity is not verified” Is done. In some implementations, binomial classification can be performed by a neural network pattern classifier, such as the neural network described below. In some implementations, binomial classification can be performed by determining the difference (or distance) between the test feature vector and the target feature vector described above.

  In the example shown in FIG. 3, test data at various times and / or information derived from it (314) is stored in the storage (316) of the smart inhaler system. Breathprint identity verification results may also be stored. Furthermore, the results can be used to control the inhaler device of the smart inhaler system. For example, in some embodiments, the inhaler device may not administer a drug if the user's identity is not verified. In other embodiments, the inhaler can issue a warning when the user's identity is not verified.

  In some embodiments of the smart inhaler system, as shown in FIG. 3, the smart inhaler system further includes information derived from the current breath print sample and one stored in memory. One or more previous breath print samples are compared (block 320). Previous breath print samples may be obtained from the same user or from other users. Based on the results of the comparison, in various embodiments, the smart inhaler system issues a warning (e.g., a biomarker change indicating a similarity or health risk between a particular user and other users with health risks). Can be issued), or a next dose command can be issued (eg, when a biomarker associated with determining an effective dosage is detected).

  Various information obtained by the smart inhaler system, including compliance data and adherence data, can be stored on the storage 316. Stored information may be exchanged with a healthcare provider via various communication interfaces, such as a wireless network interface described herein.

  FIG. 4 is a block diagram illustrating an example of a breath print sensor system 400 for verifying a user's identity based on a pattern classification of data from the sensor array 404. The sensor array 404 receives a respiratory sample as an input sample 402 that must be analyzed to determine the identity of the user providing the sample. The sensor array 404 can be implemented according to the sensors described above. The sensor array provides an output signal upon exposure to the respiratory sample. The breath print sensor system 400 then applies preprocessing and feature extraction to the sensor output signal. See block 406. Signal preprocessing includes, for example, digitization of sensor array output signals for pattern classification. Preprocessed data, such as a digital array of values, is then subjected to feature extraction, where feature vectors are extracted and provided as an input to pattern classifier 408b. Various feature extraction techniques can be used to obtain feature vectors that effectively capture and represent salient features of sensor data. The feature vector obtained by feature extraction is supplied as an input for pattern classification. See block 408. In some embodiments, pattern classification requires pattern classifier training. In the training phase, the training or learning algorithm 408a trains the pattern classifier 408b to determine whether the input has a pattern that belongs to the “verified identity” class and the “unverified identity” class. Used for. The classification result is then provided as output.

  As explained above, training data is provided during the training phase. In some embodiments, positive training data obtained from the person being tested is used to train the pattern classifier. In some embodiments, negative training data not obtained from the person is used to train the pattern classifier. After training, pattern classifier 408b may determine whether test data or feature vectors extracted from test data should be classified as “confirmed identities” or “unconfirmed identities”. The classification results depend on the classifier training, which includes knowledge of the data from the person, the data not from the person, and the identity of the source of the data. In some embodiments, additional incremental training or tuning may be performed in an unsupervised form during the testing phase, ie during normal use.

  Various methods for pattern classification can be used. An artificial neural network (ANN) such as that shown in FIG. 5 is used for pattern classification of 408 to determine the identity of the user in some embodiments. FIG. 5 is a schematic diagram of a neural network configured to perform pattern classification to determine a user's identity. This process mimics the biological sensory process of olfactory function, where the nose and brain classify different odors.

  As shown by way of example in FIG. 5, an ANN is a multilayer network (eg, a multilayer perceptron network) that includes a hidden layer in addition to an input layer and an output layer. Features are presented in the input layer, and the output layer represents the classification results. The parameters of the ANN are determined by training (supervised learning) using an algorithm such as error back propagation. A three-layer ANN is shown in FIG. 5 as an example. The number of output nodes can be two in this application, one node being similar to the information pattern of one or more training samples provided by the person whose information pattern of the test sample is verified It is for the classification of “confirmed identities”. In some embodiments, the number of input nodes is equal to the number of sensors in the array or the number of features extracted from the sensor data. One skilled in the art can implement different numbers of nodes and layers to achieve the desired performance of the ANN.

  The weight of the ANN hidden layer is determined as a result of training by presenting positive and negative samples to the network, for example using an error back-propagation algorithm. The weight is iteratively changed to reduce classification errors. In one embodiment, the patient is guided by an application running on a mobile device connected to a smart inhaler, for example, to provide his / her breath sample multiple times during the training phase. Other samples may be used as negative training examples, for example samples of environmental inspiration. This training phase is also referred to above as the registration phase.

  In some embodiments, the breath print sensor system includes a main array of sensors (also referred to as a first sensor) configured to determine a user's identity. FIG. 6A is a diagram showing an example of a response pattern of the first sensor array in the breath print sensor system. In this illustrative example, the sensor array has 16 sensors shown on the left 4 × 4 array. In some embodiments, the first sensor has a non-specific response characteristic. That is, the sensor is not specifically tuned to have different levels of response depending on the particular property. Upon exposure to the respiratory sample, the sensor produces different levels of response, as shown by the gray shades in the right 4x4 array. The sensor provides data representing various response levels, which are then processed by the breath print sensor system. In some embodiments, the data is analyzed by a pattern classifier to determine the user's identity as described above.

  In some embodiments, the breath print sensor system is an enhanced array of sensors configured to determine biological and / or environmental conditions (also referred to elsewhere in the specification as a second sensor). ) Is also included. FIG. 6B is a diagram showing an example of a response pattern of the first sensor array and the second sensor array in the breath print sensor system. As shown in the left half of the figure, the 4 × 4 main sensor array is coupled to the 1 × 4 augmented sensor array. In some embodiments, the enhanced sensor array is specifically tuned to detect one or more target compounds, such as nitric oxide (NO), allergens, or contaminants. In various embodiments, the enhanced sensor array can be tuned to have different response characteristics for various compounds. The response of the main sensor array and the enhanced sensor array is indicated by different shades of gray on the right side. The enhanced sensor array response can be used to determine various biological and / or environmental conditions. It is worth noting that the illustrated size of the array does not indicate the actual preferred size of the sensor array for determining user identity, biological conditions, or environmental conditions.

  In some embodiments, the enhanced sensor array is made and trained a priori to recognize the VOCs specific to disease-related markers. For example, an enhanced sensor array can be tuned to nitric oxide (NO), which indicates asthma severity (mild vs. severe).

  In some embodiments of the breath print sensor system with enhanced sensors, once the delivered drug is consumed, after oxidation and other physiological responses, the sensor system may have other conditions within the breath, such as It may be possible to detect medical conditions or reactions to drugs.

  In some embodiments of the breath print sensor system with enhanced sensors, the system may react to other conditions, such as environmental triggers and other medically relevant or health related conditions for the initiation of asthma attacks. Can be detected. Some implementations of the breath print sensor system may have an environmental sensor that detects environmental conditions. In some implementations, the environmental sensor can sense the environmental factor after the environmental factor interacts with the user.

In some embodiments, the sensor is tuned to distinguish various characteristics, such as user identity, disease state, drug response, and the like. In some embodiments, tuning includes hardware changes. For example, the sensors can have different coatings and coating configurations. In one example, the NO sensor resistance can vary within a range that is sensitive to different concentrations of NO. In contrast, the identity signature may be influenced by the relative concentrations of _{N 2, CO 2, O 2} , and other compounds. Thus, the identity sensor may need to be tuned differently than the NO sensor. In various embodiments, tuning can be performed by a manufacturer or a user. In some embodiments, tuning includes software or algorithm adjustments. In some embodiments, local trimming of the response characteristic is applied during tuning.

  Some embodiments are one or more second sensors having different response characteristics to a compound in a gas, the second sensor so as to distinguish between different biological conditions of the individual. A breath print sensor system having an enhanced sensor array including a second sensor to be tuned is provided. At least one processor of the breath print sensor system is configured to receive a set of supplemental data from the second sensor in response to exposure to gas exhaled by a person during the test phase. The at least one processor of the breath print sensor system is further configured to determine whether the supplemental data set is associated with a particular biological condition. In some embodiments, the second sensor array can detect nitric oxide to assess asthma severity from a respiratory sample. However, the second sensor array does not provide data for obtaining a signature related to the identity of the person providing the breath sample. Instead, the primary sensor array of the breath print sensor system can provide data for obtaining a signature associated with the person's identity.

  If a person presses a button on an inhaler without actually administering the drug to the person's respiratory system, some previously available smart inhalers indicate that the drug has been administered. Should be recorded. In some embodiments, the smart inhaler system disclosed herein can detect a user's specific oral environment and, as a result, determine that the above situation does not actually lead to drug administration to the user. It becomes like this. In addition, the smart inhaler system can determine the identity of the user and provide knowledge about whether the wrong individual is attempting to use the inhaler. Further, some embodiments of the smart inhaler system can determine whether a drug has been applied and consumed. In these embodiments, the second sensor array can be used to detect changes in one or more markers (affected by drug consumption) related to the pharmacokinetics of the drug.

  Further, in some embodiments, a smart inhaler with an enhanced sensor array can recognize VOC as a disease marker (eg, asthma severity). The smart inhaler can determine the next dose or issue a warning based on the enhanced sensor array reading. For example, a smart inhaler can determine an appropriate next dose and recommend rescue administration 3 hours after the first dose based on a person's biological response to the first dose. Can do. The biological response can be determined by an enhanced sensor array. In various embodiments, the smart inhaler can have one or more of the following functions.

  1) Patient confirmation from breath print.

  2) Determine the disease marker.

  3) Determine bad environmental / dangerous compounds in the air that are inhaled by the user and appear in the user's breath. For example, chemicals that are generally known to be unhealthy (such as toxic gases) may be recognized using a pattern recognition method by a breath print sensor system.

  4) Determine the compound that is the specific trigger for respiratory disorder. These compounds can be inhaled and are a subset of 3) above. A smart inhaler system can have the knowledge that the compound triggers a bad response of the user. This knowledge can be learned from the behavior of the smart inhaler user. This knowledge can also be provided in the database. In some embodiments, relevant data can be managed permanently (e.g., in the cloud) so that the same user with a new inhaler can still benefit from past learning of an old inhaler. It will be obtained. In some embodiments, the related compound does not need to be inhaled, but may be taken, for example (food or beverage), which may trigger a seizure. In some situations, intake of the compound may leave a breath print. People who have an allergic reaction to food additives may develop asthma attacks from consumption of food additives. The person may not know that he ate "contaminated" food, but the smart inhaler in some embodiments detects chemicals in the user's breath and provides a warning, And / or drug doses can be proposed.

  5) Determine pharmacokinetics and drug efficacy. In some embodiments, the smart inhaler can monitor the absorption, retention, and metabolism of the drug by the user via the respiratory sample. The smart inhaler can monitor the user's drug use and asthma attacks to learn how to optimize the drug for the user (eg, regarding dose, delivery time, etc.).

  6) Confirmation of the correct drug.

  FIG. 7 is a block diagram illustrating example components of a system in which some aspects of the present disclosure may be implemented over a computer network. In some embodiments, the computer network includes a wireless network component. The number, type, and arrangement of devices shown in FIG. 7 are merely shown as examples. In this example, various devices can communicate via one or more networks 517. The network 517 can include, for example, the public switched telephone network (PSTN), the Internet, and the cloud. The external devices 500a and 500b shown in FIG. 7 can communicate with the smart inhaler system 150. External devices 500a and 500b can be, for example, smartphones, cellular phones, tablet devices, and the like.

  At location 520, mobile device 500a can wirelessly communicate with smart inhaler system 150. The mobile device 500a is an example of an “external device” referred to in the above discussion. The mobile device 500a executes software to perform some of the methods described herein, eg, identification functionality, determines control signals, sends to the smart inhaler system 150, and smart inhalation Information from the inhaler system 150 can be received or information from the smart inhaler system 150 or the data center 545 can be analyzed.

  In this example, the data center 545 includes various devices that can be configured to provide health information services via the network 517. Accordingly, the data center 545 can communicate with the network 517 via the gateway 525. Switch 550 and router 555 may be configured to provide network connectivity to data center 545 devices, including storage devices 560, servers 565, and workstations 570. Although only one data center 545 is shown in FIG. 7, some implementations can include multiple data centers 545. In some implementations, the data center 545 may be implemented as part of an online healthcare related data service such as a 2net ™ service or a Healthy Circles ™ service.

  One or more types of devices in the data center 545 (or elsewhere) may be capable of executing middleware for data management and / or device communication, for example. Health-related information, including but not limited to information obtained by smart inhaler system 150 and / or other information regarding authorized users of smart inhaler system 150, is stored on storage device 560 and / or server 565. Can be done. Health related software may also be stored on the storage device 560 and / or the server 565. In some implementations, some such health-related software can be used as “apps” and can be downloaded by authorized users.

  In this example, various people and / or entities, including but not limited to healthcare professionals, patients, patient families, insurance company agents, etc., may receive information regarding or obtained from smart inhaler system 150. It can be obtained. The information can include, but is not limited to, physiological data obtained by the smart inhaler system 150, information about substances delivered by the smart inhaler system 150, and the like.

  In some embodiments, information regarding the type of substance delivered, time of substance delivery, dosage, and / or other data is transmitted over the network 571 by the smart inhaler system 150 and is It can be stored in one or more devices. Additional information such as time stamp information, authentication information, and / or location information may be associated with the substance delivery information and / or physiological data obtained by the smart inhaler system 150. In some embodiments, at least some of such information may be stored on a memory disposed within the housing that also includes the inhaler device. Such information may, for example, create a record that the substance was administered to the authorized user / patient at the specified time and / or that data was obtained from the authorized user / patient. Can be used. Such information can be used to create an audit trail. In some embodiments, such information does not require the patient in the trial to be administered the drug only at a specific location, such as a medical research center or healthcare facility, rather than mobile and / or drug related. Or it can be used to enable remote clinical trials.

  In some examples, authorized persons and / or entities may obtain such information via the data center 545. Alternatively, at least some people and / or entities may be allowed to obtain such information via a data feed from smart inhaler system 150. One or more other devices (mobile devices 500a and 500b or data center 545 devices) may act as intermediaries for such data feeds. Such a device may be capable of, for example, applying data filtering algorithms, executing data summarization and / or analysis software, and the like. In some implementations, data filtering, summarization and / or analysis software is available as an “app” and can be downloaded by an authorized user (eg, from the data center 545).

  An authorized user's family members can log into the system via the mobile device 500b to access physiological data obtained from the user by the smart inhaler system 150. FIG. 7 also shows a clinic 505 in which a health care professional 510 is using a laptop 515 to access information from the data center 545. The information may include information obtained by smart inhaler system 150 (and / or substances delivered thereby).

  The description herein is directed to certain embodiments for describing aspects of the disclosure. However, one of ordinary skill in the art will readily appreciate that the teachings herein can be applied in a number of different ways. Embodiments described include cellular phones, multimedia internet-enabled cellular phones, mobile television receivers, wireless devices, smartphones, Bluetooth® devices, personal digital assistants (PDAs), wireless email receivers, handheld computers Or a portable computer, netbook, notebook, smart book, tablet, global positioning system (GPS) receiver / navigator, camera, camcorder, watch, electronic reading device (e.g., electronic reader), mobile health device, etc. It is contemplated that included within, but not limited to, various electronic devices can be associated with it. The teachings herein include sensors including but not limited to electronic switching devices, radio frequency filters, biometric sensors, accelerometers, gyroscopes, motion sensing devices, magnetometers, home appliance inertial components, and the like. It can also be used in applications such as but not limited to. Accordingly, the teachings are not intended to be limited to the embodiments shown alone in the drawings, but have broad applicability that will be readily apparent to those skilled in the art.

  As used herein, the phrase referring to “at least one of the list of items” refers to any combination of these elements including a single element. By way of example, “at least one of a, b, or c” is intended to include a, b, c, a-b, a-c, b-c, and a-b-c.

  Various exemplary logic, logic blocks, modules, circuits, and algorithmic processes described in connection with the embodiments disclosed herein are implemented as electronic hardware, computer software, or a combination of both. Can be done. Hardware and software interchangeability is generally described in terms of functionality and illustrated in various exemplary components, blocks, modules, circuits, and processes described above. Whether such functionality is implemented in hardware or software depends upon the particular application and design constraints imposed on the overall system.

  The hardware and data processing apparatus used to implement the various exemplary logic, logic blocks, modules, and circuits described in connection with the aspects disclosed herein are general purpose single Chip or multichip processor, digital signal processor (DSP), application specific integrated circuit (ASIC), field programmable gate array (FPGA) or other programmable logic device, discrete gate logic or transistor logic, discrete hardware components, Or it may be implemented or performed using any combination thereof designed to perform the functions described herein. A general purpose processor may be a microprocessor, or any conventional processor, controller, microcontroller, or state machine. The processor may also be implemented as a combination of computing devices, eg, a DSP and microprocessor combination, multiple microprocessors, one or more microprocessors associated with a DSP core, or any other such configuration. obtain. In some embodiments, certain processes and methods may be performed by circuitry that is specific to a given function.

  In one or more embodiments, the functions described include hardware, digital electronic circuitry, computer software, firmware, or any combination thereof, including the structures disclosed herein and their structural equivalents Can be implemented. Embodiments of the subject matter described herein are encoded on a computer storage medium as one or more computer programs, ie, for execution by a data processing device or for controlling operation of a data processing device. It may also be implemented as one or more modules of computerized computer program instructions.

  When implemented in software, the functions may be stored on or transmitted over as one or more instructions or code on a computer-readable medium such as a non-transitory medium. The methods or algorithmic processes disclosed herein may be implemented in a processor-executable software module that may reside on a computer-readable medium. Computer-readable media includes both computer storage media and communication media including any medium that may be capable of transferring a computer program from one place to another. A storage media may be any available media that can be accessed by a computer. By way of example, and not limitation, non-transitory media may be RAM, ROM, EEPROM, CD-ROM or other optical disc storage, magnetic disk storage or other magnetic storage device, or instructions or data Any other medium that can be used to store the desired program code in the form of a structure and that can be accessed by a computer can be included. Also, all connections can be appropriately referred to as computer-readable media. As used herein, disks (discs) are compact discs (CDs), laser discs (discs), optical discs (discs), digital versatile discs (DVDs), floppy discs. (disk) and Blu-ray disc (disc), and disk normally reproduces data magnetically, but disc optically reproduces data using a laser. Combinations of the above should also be included within the scope of computer-readable media. Further, the operations of the method or algorithm may reside as one, any combination, or set of code and instructions on machine-readable and computer-readable media that may be incorporated within a computer program product.

  Various modifications of the embodiments described within this disclosure may be readily apparent to those skilled in the art, and the generic principles defined within this specification are within the spirit or scope of this disclosure. It can be applied to other embodiments without departing from. Accordingly, the present disclosure is not intended to be limited to the embodiments shown within this specification, but is consistent with the claims and the principles and features disclosed within this specification. Must be given the widest range. The word “exemplary” is used herein only to mean “serving as an example, instance, or illustration”. Any implementation described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other implementations. The present disclosure should not be limited except in accordance with the claims.

  Certain features that are described in this specification in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable subcombination. In addition, a feature may be described above as working in a particular combination, and even initially claimed as such, but one or more features from the claimed combination are In some cases, it may be deleted from the combination and the claimed combination may be targeted to a sub-combination or sub-combination variant.

  Similarly, operations are illustrated in a particular order in the drawings, as long as such operations are performed in the particular order or sequence illustrated, or all illustrated operations produce the desired results. It should not be understood as requiring that it be carried out in order to achieve. In certain situations, multitasking and parallel processing may be advantageous. Further, the separation of various system components in the embodiments described above should not be understood as requiring such separation in all embodiments, and the program components and systems described are: It should be understood that, in general, they may be integrated as a single software product or packaged in multiple software products. Furthermore, other embodiments are within the scope of the following claims. In some cases, the actions recited in the claims may be performed in a different order and still achieve desirable results.

  Features in any of the specific described embodiments are clearly identified as being incompatible with each other, or the surrounding context indicates that the features are mutually exclusive, meaning of complementation and / or support Unless otherwise implied that the specific features of their complementary embodiments provide one or more comprehensive but slightly different technical solutions. It will be understood that it is contemplated and envisioned that it can be selectively combined to do so. Accordingly, it will be further appreciated that the above description is provided by way of example only and modifications of detail may be made within the scope of the present disclosure.

150 smart inhaler system
152 breath print sensor system
154 Inhaler device
156 Control system
158 interface system
160 First sensor
162 Second sensor
164 memory
166 processor
200 methods
300 methods
304 training set data
314 Test data at various times and / or information derived from it
316 storage
400 breath print sensor system
402 input samples
404 sensor array
408a Training or learning algorithm
408b Pattern Classifier
500a External device
500b External device
505 clinic
510 Healthcare professionals
515 Laptop
517 network
520 position
525 gateway
545 Data Center
550 switch
555 router
560 storage devices
565 servers
570 workstation
571 network

Claims (40)

A breath print sensor system for confirming a person's identity,
One or more first sensors having a first response characteristic for a compound in a gas, wherein the one or more first sensors output sensor data representing the first response characteristic One or more first sensors, configured as
One or more processors in communication with the one or more first sensors, the one or more processors comprising:
Receiving a set of test data provided by the one or more first sensors based on exposure of the one or more first sensors to a gas created by the person during a test phase;
A breath print sensor system comprising: one or more processors configured to determine whether the set of test data confirms the identity of the person. One or more second sensors having a second response characteristic for a compound in the gas, wherein the one or more second sensors output supplemental sensor data representing the second response characteristic Further comprising one or more second sensors, wherein the one or more processors are further in communication with the one or more second sensors;
A set of supplemental sensor data provided by the one or more second sensors based on the exposure of the one or more second sensors to the gas created by the person during the testing phase. Acceptance,
Identify biological or environmental conditions associated with the set of supplemental sensor data;
The breath print sensor system of claim 1, further configured to provide information indicative of the biological condition or the environmental condition. Determining whether the set of test data confirms the identity of the person is
Pre-processing the test data;
The pre-processed test data (i) a verified identity when the test data pattern is recognized as belonging to the person and (ii) the test data pattern as not belonging to the person 3. A breath print sensor system according to claim 1 or claim 2, comprising using a pattern classifier to classify into one of a plurality of classes that include unverified identities when performed.   4. The breath print sensor system according to claim 3, wherein the pattern classifier includes a neural network pattern classifier.   5. The breath print sensor system of claim 3 or claim 4, wherein the one or more processors are further configured to train the pattern classifier from one or more sets of training data. Training the pattern classifier from one or more sets of training data
Positive training provided by the one or more first sensors based on one or more exposures of the one or more first sensors to a gas created by the person during a training phase Receiving one or more sets of data;
Providing the one or more sets of positive training data to the pattern classifier;
6. The breath print sensor system of claim 5, comprising: informing the pattern classifier that the one or more sets of positive training data belong to the person. Training the pattern classifier from one or more sets of training data
Negative negation provided by the one or more first sensors based on one or more exposures of the one or more first sensors to a gas not made by the person during the training phase Receiving one or more sets of training data;
Providing the pattern classifier with the one or more sets of negative training data;
7. The breath print sensor system of claim 6, further comprising: informing the pattern classifier that the one or more sets of negative training data do not belong to the person.   The one or more first sensors are made from a sensor material selected from the group consisting of conductive polymers, conductive polymer composites, intrinsically conductive polymers, and any combination thereof. Item 8. The breath print sensor system according to any one of Items 1 to 7.   The one or more first sensors are further configured to obtain sensor data when a surface temperature of the one or more first sensors is not modulated. The breath print sensor system according to item.   The breath print sensor system according to any one of claims 1 to 9, further comprising a memory configured to store the sensor data and / or information derived from the sensor data.   11. The breath print sensor system according to any one of claims 1 to 10, wherein each sensor includes a polymer layer having a variable conductance based on exposure to volatile organic compounds (VOC) in the gas.   12. The breath print sensor system of any one of claims 1 to 11, wherein the one or more processors are further configured to derive a test feature vector from the test data via feature extraction.   The one or more processors compare the test feature vector with a training feature vector derived from training data, and based on the comparison, determine whether the test data confirms the identity of the person. The breath print sensor system of claim 12, further configured as follows. A smart inhaler system for delivering drugs to a person by inhalation,
A breath print sensor system configured to verify the identity of the person using a gas produced by the person;
The inhaler device adapted to deliver the drug to the person via inhalation when the inhaler apparatus is received by the person;
A control system in communication with the breath print sensor system and the inhaler device, the control system comprising:
Receiving information from the breath print sensor system, the information indicating whether the person's identity is confirmed;
A smart inhaler system comprising: a control system configured to control operation of the inhaler device according to the received information.   15. The smart inhaler system according to claim 14, wherein controlling the operation of the inhaler device according to the received information includes controlling delivery of a drug according to the received information.   16. Smart inhalation according to claim 14 or 15, further comprising an interface system for inputting data into and / or outputting data from the breath printing system, the inhaler device, and / or the control system System.   The smart inhaler system of claim 16, wherein the interface system includes a wireless network interface for exchanging data with an external device over a wireless network.   18. The smart inhaler system of claim 16 or claim 17, wherein the interface system includes an input / output device configured to receive user input and provide information to the user.   19. The smart inhaler of claim 18, wherein the input / output device comprises one selected from the group consisting of a display device, a light emitting diode, a speaker, a touch sensitive input device, a button, a haptic device, and any combination thereof. system.   When the information received from the breath print sensor system indicates that the person's identity is not confirmed, the control system sends a notification indicating that the unverified person has attempted to use the inhaler device. 20. A smart inhaler system according to any one of claims 14 to 19, further configured to deliver.   15. The control system is further configured to deactivate the inhaler device when the information received from the breath print sensor system indicates that the person's identity is not verified. 21. The smart inhaler system according to any one of 20.   The control system is further configured to prompt the person to provide a breath sample to the breath print sensor system when the information received from the breath print sensor system indicates that the person's identity is not verified. The smart inhaler system according to any one of claims 14 to 21, wherein the smart inhaler system is configured.   The control system provides alternative information not derived from a breath sample to confirm the person's identity when the information received from the breath print sensor system indicates that the person's identity is not confirmed. 23. A smart inhaler system according to any one of claims 14 to 22, further configured to prompt the person.   24. A smart inhaler system according to any one of claims 14 to 23, wherein the control system includes one or more processors communicatively coupled to the breath print sensor system and the inhaler device. At least one of the processors is
Analyzing information derived from a respiratory sample made by the person and determining that the person has a respiratory disorder;
Associating said respiratory disorder with one or more environmental conditions;
Associating the one or more environmental conditions with location data;
25. The smart inhaler system of claim 24, configured to create a map of the one or more environmental conditions associated with the respiratory disorder. The breath print sensor system includes:
One or more first sensors having a first response characteristic for a compound in a gas, wherein the one or more first sensors output sensor data representing the first response characteristic One or more first sensors, configured as
One or more second sensors having a second response characteristic for a compound in the gas, wherein the one or more second sensors output supplemental sensor data representing the second response characteristic Including one or more second sensors configured to
The first response characteristic is tuned to confirm the identity of the person;
26. A smart inhaler system according to any one of claims 14 to 25, wherein the second response characteristic is tuned for one or more biological markers. The one or more biological markers relate to drug pharmacokinetics, and at least one of the processors includes:
Determining the efficacy of the dose of the drug delivered by the inhaler device using the supplemental sensor data representing the second response characteristic tuned for the one or more biological markers;
27. The smart inhaler system of claim 26, configured to determine a delivery plan for the drug based on the efficacy. A method for verifying a person's identity using a breath print sensor system that includes one or more first sensors having a first response characteristic to a compound in a gas, the method comprising:
Receiving a set of test data provided by the one or more first sensors based on exposure of the one or more first sensors to a gas produced by the person;
Determining whether the set of test data confirms the identity of the person. The breath print sensor system further includes one or more second sensors having a second response characteristic to a compound in a gas, the method comprising:
Receiving a set of supplemental sensor data provided by the one or more second sensors based on exposure of the one or more second sensors to the gas produced by the person;
Identifying a biological or environmental condition associated with the set of supplemental sensor data;
29. The method of claim 28, further comprising providing information indicative of the biological condition or the environmental condition. Determining whether the set of test data confirms the identity of the person comprises:
Pre-processing the test data;
The pre-processed test data (i) a verified identity when the test data pattern is recognized as belonging to the person and (ii) the test data pattern as not belonging to the person Using a pattern classifier to classify into one of a plurality of classes that include unverified identities when performed.   32. The method of claim 30, further comprising training the pattern classifier from one or more sets of training data prior to classifying the preprocessed test data. The step of training the pattern classifier includes:
Positive training provided by the one or more first sensors based on one or more exposures of the one or more first sensors to a gas created by the person during a training phase Receiving one or more sets of data;
Providing the pattern classifier with the one or more sets of positive training data;
32. Informing the pattern classifier that the one or more sets of positive training data belong to the person. The step of training the pattern classifier includes:
Negative negation provided by the one or more first sensors based on one or more exposures of the one or more first sensors to a gas not made by the person during the training phase Receiving one or more sets of training data;
Providing the pattern classifier with the one or more sets of negative training data;
33. The method of claim 32, further comprising: informing the pattern classifier that the one or more sets of negative training data do not belong to the person. A method for controlling a smart inhaler system comprising a breath print sensor system, an inhaler device, and one or more processors in communication with the breath print sensor system and the inhaler device comprising:
Receiving information from the breath print sensor system indicating whether the identity of the person is confirmed using a gas produced by the person;
Controlling the operation of the inhaler device according to the received information.   35. The method of claim 34, wherein controlling the operation of the inhaler device according to the received information includes controlling delivery of a drug according to the received information. Controlling the operation of the inhaler device in accordance with the received information, when the information received from the breath print sensor system indicates that the person's identity is not verified;
Sending a notification to another person notifying that an unverified person has attempted to use the inhaler device;
Deactivating the inhaler device;
Urging the person to provide a breath sample to the breath sensor system;
Urging the person to provide alternative information that is not derived from any respiratory sample to confirm the person's identity;
36. A method according to claim 34 or claim 35, comprising performing an operation selected from the group consisting of any combination thereof. A non-transitory computer readable medium storing computer readable program code executed by one or more processors, the program code having one or more first response characteristics for a compound in a gas. Breath print sensor system including 1 sensor,
Instructions for receiving a set of test data provided by the one or more first sensors based on exposure of the one or more first sensors to a gas produced by a person;
A non-transitory computer readable medium comprising: instructions for determining whether the set of test data confirms the identity of the person. Determining whether the set of test data confirms the identity of the person is
Pre-processing the test data;
The pre-processed test data (i) a verified identity when the test data pattern is recognized as belonging to the person and (ii) the test data pattern as not belonging to the person 38. The non-transitory computer-readable medium of claim 37, comprising: using a pattern classifier to classify into one of a plurality of classes that include unverified identities when being performed. The program code is supplemented to the breath print sensor system provided by the one or more second sensors based on exposure of the one or more second sensors to the gas made by the person An instruction to receive a set of sensor data;
Instructions to identify biological or environmental conditions associated with the set of supplemental sensor data;
Instructions for providing information indicative of the biological condition or the environmental condition, wherein the breath print sensor system has a second response characteristic to a compound in a gas, the one or more second sensors 39. The non-transitory computer readable medium of claim 37 or claim 38, further comprising: A non-transitory computer readable medium storing computer readable program code for execution by one or more processors, wherein the program code is stored in a smart inhaler system including a breath print sensor system and an inhaler device.
Receiving information from the breath print sensor system indicating whether the identity of the person is confirmed using a gas produced by the person;
A non-transitory computer readable medium comprising instructions configured to control operation of the inhaler device in accordance with the received information.